paper-with-me

Papers

An Enhanced Scheme for Reducing the Complexity of Pointwise Convolutions in CNNs for Image Classification Based on Interleaved Grouped Filters without Divisibility Constraints

2022-09-08 · Entropy 2022 9 · Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan, Domenec Puig

In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Existing studies demonstrated that a subnetwork can replace pointwise convolutional layers with significantly fewer parameters and fewer floating-point computations, while maintaining the learning capacity. In this paper, we propose an improved scheme for reducing the complexity of pointwise convolutions in DCNNs for image classification based on interleaved grouped filters without divisibility constraints. The proposed scheme utilizes grouped pointwise convolutions, in which each group processes a fraction of the input channels. It requires a number of channels per group as a hyperparameter Ch. The subnetwork of the proposed scheme contains two consecutive convolutional layers K and L, connected by an interleaving layer in the middle, and summed at the end. The number of groups of filters and filters per group for layers K and L is determined by exact divisions of the original number of input channels and filters by Ch. If the divisions were not exact, the original layer could not be substituted. In this paper, we refine the previous algorithm so that input channels are replicated and groups can have different numbers of filters to cope with non exact divisibility situations. Thus, the proposed scheme further reduces the number of floating-point computations (11%) and trainable parameters (10%) achieved by the previous method. We tested our optimization on an EfficientNet-B0 as a baseline architecture and made classification tests on the CIFAR-10, Colorectal Cancer Histology, and Malaria datasets. For each dataset, our optimization achieves a saving of 76%, 89%, and 91% of the number of trainable parameters of EfficientNet-B0, while keeping its test classification accuracy.

📄 PDF Abstract BibTeX

Code (2)

joaopauloschuler/k-neural-api tf
joaopauloschuler/kEffNetV2

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
NON 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Sigmoid Activation 설명 없음
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Group Shift Pointwise Convolution for Volumetric Medical Image Segmentation

2021-09-26 · Junjun He, Jin Ye, Cheng Li, Diping Song 외

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Neverthe…

Image SegmentationMedical Image SegmentationSemantic SegmentationVolumetric Medical Image Segmentation

Lite-HRNet: A Lightweight High-Resolution Network

2021-04-13 · CVPR 2021 1 · Changqian Yu, Bin Xiao, Changxin Gao, Lu Yuan 외

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performa…

Pose EstimationReal-Time Semantic SegmentationSemantic SegmentationVocal Bursts Intensity Prediction

PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs

2025-05-06 · Lukas Meiner, Jens Mehnert, Alexandru Paul Condurache

Convolutional neural networks (CNNs) are crucial for computer vision tasks on resource-constrained devices. Quantization effectively compresses these models, reducing storage size and energy cost. However, in modern dept…

Quantization

Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs

2026-08-26 · Hao Luo, Yiting Yang, Wenyi Zhao, Man Jiang 외 arxiv

Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge…

Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks

2022-06-30 · Mendel 2022 6 · Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan 외

In Deep Convolutional Neural Networks (DCNNs), the parameter count in pointwise convolutions quickly grows due to the multiplication of the filters and input channels from the preceding layer. To handle this growth, we p…

Spam detection